{"id":2379187,"url":"https://alion.io/job/clera-mid-level-research-engineer-benchmarks-2","title":"Mid-Level Research Engineer, Benchmarks","company":{"id":2706,"name":"Clera","domain":"getclera.com","url":"https://alion.io/company/clera","size_band":"11-50","is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":"Ashby","truth_index":{"grade":"B","score":80,"open_postings":30,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":6,"computed_at":"2026-10-14T06:34:16Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"middle","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Singapore"],"countries":["SG"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":100000,"max":170000,"currency":"USD","period":"year","gross":null,"usd_annual":170000},"salary_estimate":null,"experience_years_min":2,"visa_sponsorship":true,"relocation_package":false,"has_equity":false,"technologies":[{"name":"AI Agents","optional":false},{"name":"Docker","optional":false},{"name":"Linux","optional":false},{"name":"Machine Learning","optional":false},{"name":"Python","optional":false},{"name":"Reinforcement Learning","optional":false}],"status":"live","first_seen_at":"2026-10-12T17:26:46Z","employer_posted_date":"2026-10-12","last_verified_at":"2026-10-14T13:21:01Z","board_verified":true,"closed_at":null,"days_open":1,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":1},"description":"About the Role\nJoin a small, technical team at an early-stage AI evaluation infrastructure startup building benchmarks for frontier AI agents. You will own the design and implementation of rigorous evaluations for realistic, domain-specific workflows, helping technical teams understand how agent performance translates to practical settings.\nWhat You'll Do\nDesign, implement, and maintain benchmarks for evaluating frontier AI agents on domain-specific tasks.\n\nCollaborate with subject-matter experts to turn real workflows into realistic benchmark tasks and evaluation criteria.\n\nBuild reliable infrastructure to run models and agents against evaluation tasks at scale.\n\nDevelop metrics and analyses to assess benchmark difficulty, reliability, and failure modes.\n\nValidate how benchmark results relate to real-world evaluations and technical user needs.\n\nWrite clear technical documentation and reports that communicate findings to research and engineering audiences.\n\nWhat We're Looking For\nTwo or more years of experience in research engineering or machine learning engineering, with a focus on AI benchmarks, evaluation infrastructure, or agent environments.\n\nExperience designing, implementing, and operating benchmarks or evaluation environments for AI agents or large language models.\n\nProficiency in Python, Docker, and Linux environments.\n\nExperience building infrastructure to run AI models or agents reliably, and collaborating with subject-matter experts to define tasks and criteria.\n\nExperience analyzing workflows across technical or business domains, and developing metrics or validation studies for benchmark quality.\n\nStrong technical writing, attention to detail, and ability to work independently in unstructured environments.\n\nExperience with reinforcement learning pipelines, data generation, published work, or public benchmarks is beneficial.\n\nCompensation & Benefits\nAnnual salary range: $100,000 to $170,000 USD. Visa sponsorship is available.\nLocation\nOn-site in Singapore, Singapore.","description_format":"text","description_chars":2013,"description_truncated":false,"requirements":{"experience_years_min":2,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[{"name":"Singapore","iso":"SG","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-10-12T19:02:37Z"}],"visa":[],"liveness":{"score":36,"band":"fade","label":"Fading","p_open":1,"p_active":0.361,"p_room":1,"age_days":1,"expected_fill_days":6,"reasons":["conf:2","agency","stale_co","win:early","comp:brand"],"computed_at":"2026-10-14T06:34:16Z"},"pay":{"stated_usd_annual":170000,"is_top_pay":false},"html_url":"https://alion.io/job/clera-mid-level-research-engineer-benchmarks-2","json_url":"https://alion.io/job/clera-mid-level-research-engineer-benchmarks-2.json","meta":{"generated_at":"2026-10-14T16:00:28Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":20366,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-15T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":2706},"rest":"https://alion.io/mcp/rest/get_company?id=2706"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fclera-mid-level-research-engineer-benchmarks-2"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fclera-mid-level-research-engineer-benchmarks-2"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fclera-mid-level-research-engineer-benchmarks-2"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/clera-mid-level-research-engineer-benchmarks-2\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fclera-mid-level-research-engineer-benchmarks-2"}]}